© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46120
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parentheses or digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebel
    -0.09
    å¼ı设计
    -0.09
    elib
    -0.08
    åIJIJ
    -0.08
    ush
    -0.07
    _PRIORITY
    -0.07
    ä¸Ģ转
    -0.07
    endorf
    -0.07
     porti
    -0.07
    æľŁ
    -0.07
    POSITIVE LOGITS
    å®īåħ¨ç¨³å®ļ
    0.06
    hire
    0.06
    nett
    0.06
    Configs
    0.06
    æĵº
    0.06
    aven
    0.06
    kop
    0.06
    Ùħز
    0.06
    kk
    0.06
     commenter
    0.06
    Activations Density 0.019%

    No Known Activations